用 LoRA、Adapter 等少量参数微调大模型和扩散模型，大幅降低显存与训练成本，是 Hugging Face 生态里做参数高效微调的标准库。
命令行工具，引导你按约定格式填写 Git 提交信息，方便生成变更日志和语义化版本发布。
…e Transformers v4.57.x . New Add support for DoRA adapters (@julian-fong via 790): DoRA ([Liu et al., 2024](https://arxiv.org/pdf/2402.09353)) is an enhanced LoRA variant
Blog post: https://adapterhub.ml/blog/2025/05/adapters-for-any-transformer This version is built for Hugging Face Transformers v4.51.x . New Adapter Model Plugin Interfac
…t for Hugging Face Transformers v4.47.x . New Add AdapterPlus adapters (@julian-fong via 746, 775): AdapterPlus ([Steitz & Roth, 2024](https://openaccess.thecvf.com/conte
…dded - Add cookbook for E2E RAG with ColQwen2 and adapter hot-swapping Full Changelog : https://github.com/tonywu71/colpali-cookbooks/compare/v0.2.1...v0.3.0
…e [notebook for ReFT training](https://github.com/Adapter-Hub/adapters/blob/main/notebooks/ReFT Adapters Finetuning.ipynb) (@julian-fong via 741) Changes - Upgrade suppor
Like 0.2.0 but with qpth made optional.